202 lines
5.1 KiB
JSON
202 lines
5.1 KiB
JSON
[
|
|
{
|
|
"test_name": "test_voxcpm2",
|
|
"server_params": {
|
|
"model": "openbmb/VoxCPM2",
|
|
"trust_remote_code": true,
|
|
"extra_cli_args": [
|
|
"--trust-remote-code"
|
|
]
|
|
},
|
|
"benchmark_params": [
|
|
{
|
|
"task": "voice_clone",
|
|
"eval_phase": "latency",
|
|
"dataset_name": "seed-tts",
|
|
"backend": "openai-audio-speech",
|
|
"endpoint": "/v1/audio/speech",
|
|
"dataset_path": "linyueqian/seed-tts-eval-subset",
|
|
"num_prompts": [
|
|
20
|
|
],
|
|
"max_concurrency": [
|
|
1
|
|
],
|
|
"seed_tts_locale": "en",
|
|
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
|
|
"baseline": {
|
|
"median_audio_ttfp_ms": [
|
|
130.2115
|
|
],
|
|
"median_audio_rtf": [
|
|
0.0488
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"task": "voice_clone",
|
|
"eval_phase": "throughput",
|
|
"dataset_name": "seed-tts",
|
|
"backend": "openai-audio-speech",
|
|
"endpoint": "/v1/audio/speech",
|
|
"dataset_path": "linyueqian/seed-tts-eval-subset",
|
|
"num_prompts": [
|
|
80
|
|
],
|
|
"max_concurrency": [
|
|
8
|
|
],
|
|
"seed_tts_locale": "en",
|
|
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
|
|
"baseline": {
|
|
"median_audio_ttfp_ms": [
|
|
475.3357
|
|
],
|
|
"median_audio_rtf": [
|
|
0.1671
|
|
],
|
|
"audio_throughput": [
|
|
22.8717
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"task": "voice_clone",
|
|
"eval_phase": "quality",
|
|
"enabled": false,
|
|
"dataset_name": "seed-tts",
|
|
"backend": "openai-audio-speech",
|
|
"endpoint": "/v1/audio/speech",
|
|
"dataset_path": "linyueqian/seed-tts-eval-subset",
|
|
"num_prompts": [
|
|
200
|
|
],
|
|
"max_concurrency": [
|
|
4
|
|
],
|
|
"seed_tts_locale": "en",
|
|
"seed_tts_wer_eval": true,
|
|
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
|
|
"baseline": {
|
|
"mean_audio_rtf": [
|
|
0.45
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"task": "default_voice",
|
|
"eval_phase": "latency",
|
|
"dataset_name": "seed-tts-text",
|
|
"backend": "openai-audio-speech",
|
|
"endpoint": "/v1/audio/speech",
|
|
"dataset_path": "benchmarks/build_dataset/seed_tts_smoke",
|
|
"num_prompts": [
|
|
20
|
|
],
|
|
"max_concurrency": [
|
|
1
|
|
],
|
|
"seed_tts_locale": "en",
|
|
"extra_body": {
|
|
"voice": "default"
|
|
},
|
|
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
|
|
"baseline": {
|
|
"median_audio_ttfp_ms": [
|
|
75.7427
|
|
],
|
|
"median_audio_rtf": [
|
|
0.0419
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"task": "default_voice",
|
|
"eval_phase": "throughput",
|
|
"dataset_name": "seed-tts-text",
|
|
"backend": "openai-audio-speech",
|
|
"endpoint": "/v1/audio/speech",
|
|
"dataset_path": "benchmarks/build_dataset/seed_tts_smoke",
|
|
"num_prompts": [
|
|
80
|
|
],
|
|
"max_concurrency": [
|
|
8
|
|
],
|
|
"seed_tts_locale": "en",
|
|
"extra_body": {
|
|
"voice": "default"
|
|
},
|
|
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
|
|
"baseline": {
|
|
"median_audio_ttfp_ms": [
|
|
351.5855
|
|
],
|
|
"median_audio_rtf": [
|
|
0.1207
|
|
],
|
|
"audio_throughput": [
|
|
73.7632
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"task": "default_voice",
|
|
"eval_phase": "stress",
|
|
"dataset_name": "seed-tts-text",
|
|
"backend": "openai-audio-speech",
|
|
"endpoint": "/v1/audio/speech",
|
|
"dataset_path": "benchmarks/build_dataset/seed_tts_smoke",
|
|
"num_prompts": [
|
|
100
|
|
],
|
|
"request_rate": [
|
|
2.0
|
|
],
|
|
"seed_tts_locale": "en",
|
|
"extra_body": {
|
|
"voice": "default"
|
|
},
|
|
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
|
|
"baseline": {
|
|
"median_audio_ttfp_ms": [
|
|
80.1095
|
|
],
|
|
"median_audio_rtf": [
|
|
0.0485
|
|
],
|
|
"audio_throughput": [
|
|
18.3715
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"task": "default_voice",
|
|
"eval_phase": "quality",
|
|
"enabled": false,
|
|
"dataset_name": "seed-tts-text",
|
|
"backend": "openai-audio-speech",
|
|
"endpoint": "/v1/audio/speech",
|
|
"dataset_path": "benchmarks/build_dataset/seed_tts_smoke",
|
|
"num_prompts": [
|
|
200
|
|
],
|
|
"max_concurrency": [
|
|
4
|
|
],
|
|
"seed_tts_locale": "en",
|
|
"extra_body": {
|
|
"voice": "default"
|
|
},
|
|
"seed_tts_wer_eval": true,
|
|
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
|
|
"baseline": {
|
|
"mean_audio_rtf": [
|
|
0.35
|
|
]
|
|
}
|
|
}
|
|
]
|
|
}
|
|
]
|